"The Cognitive Revolution"
01:16:05 · Nathan Labenz
He asked how withholding would actually work. I haven't seen really anything to date that has shown a unlearning, you know, in a really profound or successful way or that refusals can be made super reliable or that, like, you know, tamper proofing can really work. If you're actually, you know, giving people the weights and they, you know, can obviously modify the weights however they want. So that has not seemed super promising to me, although, you know, I'm always eager to hear about a breakthrough. It feels to me like that is quite different though from a scheme where the model just doesn't learn certain things in the first place. And I really think we could use a ton more science around that. Whether it is localizing knowledge to to particular experts or pretraining filtering, there's, of course, the galaxy brain take that, like, you know, you have this whole world model, and then you have, like, one little gap in it, and you'll be able to fill in those gaps. I think there's, like, probably some truth to that, but there's some gap clearly that, like, would be big enough that you would not be able to fill in the dangerous parts with the high resolution, you know, that you would need to actually do bad things in the world. This is the sort of thing that I think that excess compute, you know, could really, be very productively used for at the frontier companies. It would be amazing for them to say, like, here's kind of how big of a knowledge gap you have to leave in a model for that to be, like, meaningfully hard, you know, for the... The model's not just gonna, you know, fill it in via insight. And, also, like, you're not just gonna be able to do, like, a couple, you know, marginal documents worth of training and kind of fill in that that gap in the way that we do see refusal being, like, removed at, you know, generally speaking, like a pretty small, like, almost like vanishingly small amount of additional training. So I would love to understand that stuff better. Yes. Like, really determined people can set up their own cluster, collect their own bio dataset, and, you know, do the additional training on top of the open weight model to create the dangerous thing. And, like, probably at some point that happens, but that's, like, more than just needing a few GPUs. Right? That's more than, like... That's like a real effort.
01:18:34 · Nathan Labenz, Prakash Narayanan
So you you would need multiple kinds of expertise. Like, that data is not that accessible. There are these, like, you know, moves to try to rein in that data and not let it, you know, just hang out all over the Internet. Prakash had heard a claim that morning that Claude was refusing to help clone video games. [01:18:56] S6: I I think I think what I fear is that they're pissing off the gamers. Right? And gaming. And you say Claude is not gonna help you, like, make these games? You're just asking for trouble. You're asking for the most security competent group, the most technically competent, and the people with the most time to burn, and it's a passion for them. NVIDIA was built on gamers. Like, John Carmack was a gamer. Right? You tell John Carmack that he can't do something. Like, you are in trouble. Right?
01:19:30 · Nathan Labenz
[01:19:30] S0: I I think that's apt. I mean, you... I think it is definitely the case that, like, we should be pretty cautious around where we deploy these things because we don't want to burn them on stupid things that don't really matter that much. It'll be like, you know, of all the ways to fail in this, it'll be really dumb if it's like, well, we were interested in protecting, you know, Disney IP. And so because of that, we, like, put in these guardrails, but then, you know, the fan fic community was so strong that they came over the top and, like, broke all of our safeguards. And now everything's, like, running wild, and it all was because, like, we were too draconian on things that didn't really matter. I mean, that's a bit of a caricature story, but it's... You know, that's basically the same story as the gaming one you're telling. And I can see that happening in different domains, and it really would be incredibly stupid. So I I do think we need to be, you know, pretty disciplined about, like, just how far we try to create these, like, knowledge gaps or refusals because everyone does potentially mobilize another community to try to undo them. And I agreed too that you're not gonna convince gamers that, like, well, hey. Because you're doing this, you know, you're creating this other downstream problem. Well, good luck having that. You know, you're not gonna win that fight in the Discord. So better to just probably let them have their fun and then, you know, keep our key techniques where we, like, really, really care and really have to have them. One more from Friday's closing right after Sagar left. Mistral's technical report and a Claude four system card story I told from memory. The card itself says, Anthropic had mistakenly omitted the only fine tuning dataset that included harmful system prompts, and that this was not the sole cause. So I'll be very interested to read the more open report on exactly, and hopefully, you know, we'll see how how open they are about all of the technical details. There have been these, like, footnotes in multiple system card reports over time. One that I really was kind of obsessed with for a minute was when... So Anthropic had forgotten to include a particular dataset called sysprompt harmful, which was meant to teach the model that it should not respond...
01:22:05 · Nathan Labenz, S7
You know, it should not directly follow a harmful system prompt. So it did follow the directions of a harmful system prompt, and this made it all the way through to the model card. We don't roll back and, you know, train again. Nope. We just kinda figure out a way to patch. I've really been very curious as to, like, how that stuff actually works and, like, how reliably we should think of it as working. That's the week. Thanks for listening to the AI and the AM weekly highlights. The narration was my cloned voice. Please tell us what worked and what didn't. See you in the morning. [01:23:31] S7: Aimed out and let her go. Ain't no calling her back. Water flat as a plate. All we do now is wait. This is the one we've got. The one we've got. Halfway out, something knocking, something wrong down below. Can't turn around, can't stop or grease up to the elbow. All hands all night. Nobody's saying it's fine. Come on in one or two ways. Everybody happy or everybody sad. No in between or halfway. Hold on. Hold on. Hold on. Hold on. This is the one we've got. The one we've Waterline keeps rising, call goes out for one more hand. There's a faith in fixing.
01:23:31 · S7, Nathan Labenz
[01:23:31] S7: Aimed out and let her go. Ain't no calling her back. Water flat as a plate. All we do now is wait. This is the one we've got. The one we've got. Halfway out, something knocking, something wrong down below. Can't turn around, can't stop or grease up to the elbow. All hands all night. Nobody's saying it's fine. Come on in one or two ways. Everybody happy or everybody sad. No in between or halfway. Hold on. Hold on. Hold on. Hold on. This is the one we've got. The one we've Waterline keeps rising, call goes out for one more hand. There's a faith in fixing. [01:25:53] S0: If you're finding value in the show, we'd appreciate it if you'd take a moment to share it with friends, post online, write a review on Apple Podcasts or Spotify, or just leave us a comment on YouTube. Of course, we always welcome your feedback, guest and topic suggestions, and sponsorship inquiries, either via our website, cognitive revolution dot a I, or by DMing me on your favorite social network. The Cognitive Revolution is part of the Turpentine Network, a network of podcasts which is now part of a sixteen z, where experts talk technology, business, economics, geopolitics, culture, and more. We're produced by AI Podcasting. If you're looking for podcast production help for everything from the moment you stop recording to the moment your audience starts listening, check them out and see my endorsement at aipodcast.ing. And thank you to everyone who listens for being part of the Cognitive Revolution.